Hugging Face's logo

NewEden-Forge
/
chat-24b

Safetensors
mistral
Model card Files
xet
Community
chat-24b
File size: 3,277 Bytes
23c31bf
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
 
{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 8.0,
  "eval_steps": 500,
  "global_step": 16,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 171.21589855027844,
      "learning_rate": 2e-05,
      "loss": 3.1436,
      "step": 1
    },
    {
      "epoch": 1.0,
      "grad_norm": 171.21589855027844,
      "learning_rate": 4e-05,
      "loss": 6.2428,
      "step": 2
    },
    {
      "epoch": 1.6666666666666665,
      "grad_norm": 471.01340030167887,
      "learning_rate": 6.000000000000001e-05,
      "loss": 9.1236,
      "step": 3
    },
    {
      "epoch": 2.0,
      "grad_norm": 1490.2938502466984,
      "learning_rate": 8e-05,
      "loss": 12.0519,
      "step": 4
    },
    {
      "epoch": 2.6666666666666665,
      "grad_norm": 942.081671418508,
      "learning_rate": 0.0001,
      "loss": 11.5508,
      "step": 5
    },
    {
      "epoch": 3.0,
      "grad_norm": 942.081671418508,
      "learning_rate": 9.900990099009903e-05,
      "loss": 10.2465,
      "step": 6
    },
    {
      "epoch": 3.6666666666666665,
      "grad_norm": 614.2143809762082,
      "learning_rate": 9.782608695652174e-05,
      "loss": 9.6248,
      "step": 7
    },
    {
      "epoch": 4.0,
      "grad_norm": 206.13959236392643,
      "learning_rate": 9.638554216867471e-05,
      "loss": 9.0348,
      "step": 8
    },
    {
      "epoch": 4.666666666666667,
      "grad_norm": 310.4054985828841,
      "learning_rate": 9.45945945945946e-05,
      "loss": 24.1443,
      "step": 9
    },
    {
      "epoch": 5.0,
      "grad_norm": 310.4054985828841,
      "learning_rate": 9.230769230769229e-05,
      "loss": 13.3258,
      "step": 10
    },
    {
      "epoch": 5.666666666666667,
      "grad_norm": 369.6066414261131,
      "learning_rate": 8.92857142857143e-05,
      "loss": 10.9274,
      "step": 11
    },
    {
      "epoch": 6.0,
      "grad_norm": 64.75267375733827,
      "learning_rate": 8.510638297872342e-05,
      "loss": 8.5392,
      "step": 12
    },
    {
      "epoch": 6.666666666666667,
      "grad_norm": 32.39084296483837,
      "learning_rate": 7.894736842105262e-05,
      "loss": 8.531,
      "step": 13
    },
    {
      "epoch": 7.0,
      "grad_norm": 32.39084296483837,
      "learning_rate": 6.896551724137931e-05,
      "loss": 7.9085,
      "step": 14
    },
    {
      "epoch": 7.666666666666667,
      "grad_norm": 254.05049483006297,
      "learning_rate": 5e-05,
      "loss": 7.8081,
      "step": 15
    },
    {
      "epoch": 8.0,
      "grad_norm": 179.19756327998078,
      "learning_rate": 0,
      "loss": 7.6925,
      "step": 16
    }
  ],
  "logging_steps": 1,
  "max_steps": 16,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 16,
  "save_steps": 1,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 6340688404807680.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}